CaltechAUTHORS
  A Caltech Library Service

Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization

Zhou, Jiaji and Ross, Stephane and Yue, Yisong and Dey, Debadeepta and Bagnell, J. Andrew (2013) Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization. In: Inferning: Interactions between Inference and Learning (WINFERN), 20 June 2013, Atlanta, GA. (Submitted) https://resolver.caltech.edu/CaltechAUTHORS:20190327-085828098

[img] PDF - Submitted Version
Creative Commons Attribution Non-commercial Share Alike.

215Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190327-085828098

Abstract

We study the problem of predicting a set or list of options under knapsack constraint. The quality of such lists are evaluated by a submodular reward function that measures both quality and diversity. Similar to DAgger (Ross et al., 2010), by a reduction to online learning, we show how to adapt two sequence prediction models to imitate greedy maximization under knapsack constraint problems: CONSEQOPT (Dey et al., 2012) and SCP (Ross et al., 2013). Experiments on extractive multi-document summarization show that our approach outperforms existing state-of-the-art methods.


Item Type:Conference or Workshop Item (Poster)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/1308.3541arXivDiscussion Paper
https://openreview.net/forum?id=7l8zgqCszj7spOrganizationDiscussion Paper
ORCID:
AuthorORCID
Yue, Yisong0000-0001-9127-1989
Additional Information:© 2013 by the author(s). Presented at the International Conference on Machine Learning (ICML) workshop on Inferning: Interactions between Inference and Learning, Atlanta, Georgia, USA, 2013. This research was supported by NSF NRI Purposeful Prediction and the Intel Science and Technology Center on Embedded Computing. We gratefully thank Martial Hebert for valuable discussions and Alex Kulesza for providing data and code.
Funders:
Funding AgencyGrant Number
NSFUNSPECIFIED
Intel Science and Technology Center for Embedded ComputingUNSPECIFIED
Record Number:CaltechAUTHORS:20190327-085828098
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190327-085828098
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94185
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:27 Mar 2019 23:15
Last Modified:03 Oct 2019 21:01

Repository Staff Only: item control page